Authors:-Kokila Ramesh, Anita Chaturvedi, Radha Gupta
Abstract:-Variability in monsoon rainfall is a natural hazard that India faces every year. The total seasonal precipitation in the month of June, July, August and September is generally known as southwest monsoon (SWM) rainfall. While the season recurs annually, the variation about the long term expected value can be as high as 40-50% in some parts of the country. The hazard due to droughts and floods caused by extreme variations can be mitigated to some extent if the rainfall time series can be modeled efficiently for simulation and forecasting. Rainfall data is a strongly non-Gaussian time series exhibiting non-stationarity. Artificial neural network (ANN) models are known to be versatile in handling such complex and unstructured data. In this paper a new ANN model general enough to model the available century long data in several sub regions of India is developed. The model is found to be efficient in explaining nearly 80% of the data variance. One year ahead forecast on a set of data, independent from the training period is also found to perform very well.
Full Issue
| View or download the full issue | PDF 1-21 |